Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3077
    Prev
    Next
    INDEX
    Explanations

    terms related to crime and evil acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.01
    2:0.04
    3:0.35
    4:0.02
    5:0.06
    6:0.04
    7:0.03
    8:0.02
    9:0.02
    10:0.27
    11:0.07
    Negative Logits
    )))
    -2.56
    �
    -2.54
    ))))
    -2.52
    ˈ
    -2.36
    >)
    -2.28
    )\
    -2.25
    )</
    -2.24
    ))
    -2.21
    ?]
    -2.20
     )))
    -2.15
    POSITIVE LOGITS
    "!
    4.19
    ".
    3.82
    "...
    3.31
    "…
    3.25
    ";
    3.18
    ."
    3.17
    ".[
    3.13
    ",
    3.13
    ").
    2.99
    ":
    2.98
    Activations Density 0.073%

    No Known Activations